search

fchollet / deep-learning-models

Keras code and weights files for popular deep learning models.
MIT License
7.32k stars 2.46k forks source link

Extracting features from intermediate layers of ResNet50 #81

Closed fmaglia closed 6 years ago

fmaglia commented 6 years ago

Dear all,

I'm trying to extract features from the last convolutional layer of ResNet50, but there is no name label for this layer.

x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a') x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b') x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c') x = AveragePooling2D((7, 7), name='avg_pool')(x)

How can I solve my problem?

Thanks :)